[RFC mptcp-next v2 6/7] nvme-tcp: add mptcp support

Geliang Tang posted 7 patches 1 day, 1 hour ago
[RFC mptcp-next v2 6/7] nvme-tcp: add mptcp support
Posted by Geliang Tang 1 day, 1 hour ago
From: Geliang Tang <tanggeliang@kylinos.cn>

This patch defines a new nvmf_transport_ops named nvme_mptcp_transport,
which is almost the same as nvme_tcp_transport except .type.

Check if opts->transport is "mptcp" in nvme_tcp_alloc_queue() to decide
whether to pass IPPROTO_MPTCP to sock_create_kern() to create a MPTCP
socket instead of a TCP one.

v2:
 - use 'trtype' instead of '--mptcp' (Hannes)

v3:
 - check mptcp protocol from opts->transport instead of passing a
parameter (Hannes).

v4:
 - check CONFIG_MPTCP.

Co-developed-by: Hui Zhu <zhuhui@kylinos.cn>
Signed-off-by: Hui Zhu <zhuhui@kylinos.cn>
Co-developed-by: Gang Yan <yangang@kylinos.cn>
Signed-off-by: Gang Yan <yangang@kylinos.cn>
Co-developed-by: zhenwei pi <zhenwei.pi@linux.dev>
Signed-off-by: zhenwei pi <zhenwei.pi@linux.dev>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 drivers/nvme/host/tcp.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 6795b8286c35..383e56ccc539 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -19,6 +19,7 @@
 #include <linux/blk-mq.h>
 #include <net/busy_poll.h>
 #include <trace/events/sock.h>
+#include <net/mptcp.h>
 
 #include "nvme.h"
 #include "fabrics.h"
@@ -1766,6 +1767,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 {
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
+	int proto = IPPROTO_TCP;
 	int ret, rcv_pdu_size;
 	struct file *sock_file;
 
@@ -1782,9 +1784,14 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 		queue->cmnd_capsule_len = sizeof(struct nvme_command) +
 						NVME_TCP_ADMIN_CCSZ;
 
+#ifdef CONFIG_MPTCP
+	if (!strcmp(ctrl->ctrl.opts->transport, "mptcp"))
+		proto = IPPROTO_MPTCP;
+#endif
+
 	ret = sock_create_kern(current->nsproxy->net_ns,
 			ctrl->addr.ss_family, SOCK_STREAM,
-			IPPROTO_TCP, &queue->sock);
+			proto, &queue->sock);
 	if (ret) {
 		dev_err(nctrl->device,
 			"failed to create socket: %d\n", ret);
@@ -1801,9 +1808,13 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 	nvme_tcp_reclassify_socket(queue->sock);
 
 	/* Single syn retry */
+	proto == IPPROTO_MPTCP ?
+	mptcp_sock_set_syncnt(queue->sock->sk, 1) :
 	tcp_sock_set_syncnt(queue->sock->sk, 1);
 
 	/* Set TCP no delay */
+	proto == IPPROTO_MPTCP ?
+	mptcp_sock_set_nodelay(queue->sock->sk) :
 	tcp_sock_set_nodelay(queue->sock->sk);
 
 	/*
@@ -3022,6 +3033,19 @@ static struct nvmf_transport_ops nvme_tcp_transport = {
 	.create_ctrl	= nvme_tcp_create_ctrl,
 };
 
+static struct nvmf_transport_ops nvme_mptcp_transport = {
+	.name		= "mptcp",
+	.module		= THIS_MODULE,
+	.required_opts	= NVMF_OPT_TRADDR,
+	.allowed_opts	= NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
+			  NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO |
+			  NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST |
+			  NVMF_OPT_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES |
+			  NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE | NVMF_OPT_TLS |
+			  NVMF_OPT_KEYRING | NVMF_OPT_TLS_KEY | NVMF_OPT_CONCAT,
+	.create_ctrl	= nvme_tcp_create_ctrl,
+};
+
 static int __init nvme_tcp_init_module(void)
 {
 	unsigned int wq_flags = WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_SYSFS;
@@ -3047,6 +3071,7 @@ static int __init nvme_tcp_init_module(void)
 		atomic_set(&nvme_tcp_cpu_queues[cpu], 0);
 
 	nvmf_register_transport(&nvme_tcp_transport);
+	nvmf_register_transport(&nvme_mptcp_transport);
 	return 0;
 }
 
@@ -3054,6 +3079,7 @@ static void __exit nvme_tcp_cleanup_module(void)
 {
 	struct nvme_tcp_ctrl *ctrl;
 
+	nvmf_unregister_transport(&nvme_mptcp_transport);
 	nvmf_unregister_transport(&nvme_tcp_transport);
 
 	mutex_lock(&nvme_tcp_ctrl_mutex);
-- 
2.51.0